Using Context Events in Neural Network Models for Event Temporal Status Identification

TL;DR

This paper introduces a neural network approach that leverages dependency chains of context events to improve the accuracy of identifying event temporal status, outperforming previous local context methods.

Contribution

It proposes using dependency chain representations of context events as input to neural networks, enhancing event temporal status identification accuracy.

Findings

Dependency chain input improves model performance.

Visualization confirms the importance of context events.

Outperforms previous local context models.

Abstract

Focusing on the task of identifying event temporal status, we find that events directly or indirectly governing the target event in a dependency tree are most important contexts. Therefore, we extract dependency chains containing context events and use them as input in neural network models, which consistently outperform previous models using local context words as input. Visualization verifies that the dependency chain representation can effectively capture the context events which are closely related to the target event and play key roles in predicting event temporal status.